codasms-mcp
Enables AI agents to purchase phone numbers and retrieve one-time SMS/OTP verification codes via the CODASMS API, with support for 700+ services and 180+ countries including automatic refunds if no code arrives.
README
<div align="center">
CODASMS MCP Server
Receive one-time SMS/OTP verification codes from your AI agent. An MCP server over the CODASMS Reseller API — get a number, wait for the code, release it — across 700+ services and 180+ countries, pay only on delivery.
</div>
This server lets an AI agent (Claude Desktop, Cursor, or anything that speaks MCP) buy a phone number and read the verification code programmatically. It's a thin wrapper over the public CODASMS Reseller API — it holds no logic of its own; every charge and refund is decided server-side by the API.
You bring your own key. Getting one is free to sign up: https://codasms.com/reseller.
Tools
| Tool | What it does |
|---|---|
get_balance |
Your current spendable balance. |
list_services |
Buyable services with live price + stock (filter by service / country). |
list_countries |
Countries with buyable numbers (optional service filter). |
get_number |
Buy a number for a service+country. Charges your balance (auto-refunds if no code in 20 min). |
wait_for_otp |
Poll an order until the code arrives (or timeout / refund). |
check_order |
One-shot status check for an order. |
release |
Cancel an order and refund now (unless the code already arrived). |
get_number accepts an optional max_price_cents (or set CODASMS_MAX_PRICE_CENTS) so an
autonomous agent can't buy a number priced above your cap.
Quick start (local / stdio)
export CODASMS_API_KEY=coda_live_xxxxxxxx # from https://codasms.com/reseller
npx codasms-mcp
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"codasms": {
"command": "npx",
"args": ["-y", "codasms-mcp"],
"env": { "CODASMS_API_KEY": "coda_live_xxxxxxxx" }
}
}
}
Then ask: "Get me a Telegram number in the UK and read the code."
Remote (HTTP) mode
The same tools are served over Streamable HTTP, so you can host one instance for many users — each sends their own key as a Bearer token (nothing is stored server-side):
npm run build && npm run start:http # listens on :8080, POST /mcp
POST /mcp
Authorization: Bearer coda_live_xxxxxxxx
Content-Type: application/json
src/http.ts is a portable Node server (Deno Deploy, Railway, Fly, any container). For
Cloudflare Workers, swap the Node http handler for a fetch handler — the server factory in
src/server.ts is transport-agnostic and stays unchanged.
Configuration
| Env var | Purpose | Default |
|---|---|---|
CODASMS_API_KEY |
Your coda_live_ reseller key (stdio mode). |
— (required) |
CODASMS_API_BASE |
API base URL. | https://api.codasms.com |
CODASMS_MAX_PRICE_CENTS |
Global cap for get_number, in US cents. |
unset |
PORT |
HTTP mode port. | 8080 |
Notes
- Rate limit: the API allows 60 requests/min per key;
wait_for_otppolls no faster than once every 5s by default to stay well under it. - Money safety:
get_numberspends real balance the moment it's called. If no code arrives, the order auto-refunds after 20 minutes, or callreleaseto refund immediately. - Codes: services and countries use the API's codes (e.g.
tg,wa, country6) — uselist_services/list_countriesto discover them.
Develop
npm install
npm run build # tsc -> dist/
npm start # stdio
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。